Neural Network Based Framework for Passive Intermodulation Cancellation in MIMO Systems
Xiaolong Li, Zhi-Qin John Xu, Peiting You, Yifei Zhu
TL;DR
The paper tackles passive intermodulation (PIM) interference in MIMO-OFDM systems by learning a compact nonlinear mapping $f_\theta(\mathbf{x})$ to approximate the PIM function $\mathbf{z} = f(\mathbf{x})$ from training pairs. It introduces a lightweight neural framework that combines depthwise separable and dilated convolutions, with a static-task LUT+ReLU branch and a dynamic-task CNN+FC+Sigmoid branch, trained under a cyclic learning-rate schedule and regularized by gradient clipping and weight decay. The approach achieves up to $\approx 29$ dB average power error (APE) with as few as $11{,}856$ parameters in static settings and maintains strong performance in dynamic, time-varying scenarios across multiple channels. This demonstrates that highly accurate PIM cancellation can be achieved with small, scalable architectures suitable for real-time deployment in 5G and beyond, enabling more robust interference mitigation in future wireless networks.
Abstract
Passive intermodulation (PIM) has emerged as a critical source of self-interference in modern MIMO-OFDM systems, especially under the stringent requirements of 5G and beyond. Conventional cancellation methods often rely on complex nonlinear models with limited scalability and high computational cost. In this work, we propose a lightweight deep learning framework for PIM cancellation that leverages depthwise separable convolutions and dilated convolutions to efficiently capture nonlinear dependencies across antennas and subcarriers. To further enhance convergence, we adopt a cyclic learning rate schedule and gradient clipping. In a controlled MIMO experimental setup, the method effectively suppresses third-order passive intermodulation (PIM) distortion, achieving up to 29dB of average power error (APE) with only 11k trainable parameters. These results highlight the potential of compact neural architectures for scalable interference mitigation in future wireless communication systems.